Machine learning based peri-surgical risk calculator for abdominal related emergency general surgery: a multicenter retrospective study.

BACKGROUND: Currently, there is a lack of ideal risk prediction tools in the field of emergency general surgery (EGS). The American Association for the Surgery of Trauma recommends developing risk assessment tools specifically for EGS-related diseases. In this study, we sought to utilize machine learning (ML) algorithms to explore and develop a web-based calculator for predicting five perioperative risk events of eight common operations in EGS. METHOD: This study focused on patients with EGS and utilized electronic medical record systems to obtain data retrospectively from five centers in China. Five ML algorithms, including Random Forest (RF), Support Vector Machine, Naive Bayes, XGBoost, and Logistic Regression, were employed to construct predictive models for postoperative mortality, pneumonia, surgical site infection, thrombosis, and mechanical ventilation >48 h. The optimal models for each outcome event were determined based on metrics, including the value of the Area Under the Curve, F1 score, and sensitivity. A comparative analysis was conducted between the optimal models and Emergency Surgery Score (ESS), Acute Physiology and Chronic Health Evaluation II (APACHE II) score, and American Society of Anesthesiologists (ASA) classification. A web-based calculator was developed to determine corresponding risk probabilities. RESULT: Based on 10 993 patients with EGS, we determined the optimal RF model. The RF model also exhibited strong predictive performance compared with the ESS, APACHE II score, and ASA classification. Using this optimal model, the authors developed an online calculator with a questionnaire-guided interactive interface, catering to both the preoperative and postoperative application scenarios. CONCLUSIONS: The authors successfully developed an ML-based calculator for predicting the risk of postoperative adverse events in patients with EGS. This calculator accurately predicted the occurrence risk of five outcome events, providing quantified risk probabilities for clinical diagnosis and treatment.

Prevalence and Risk Factors of Stress Urinary Incontinence Among Perimenopausal Women and Its Influence on Daily Life in Women with Sexual Desire Problem.

The prevalence of, and related factors to, stress urinary incontinence (SUI) among perimenopausal Chinese women and its impact on daily life among those women with sexual desire problem in Hubei province were investigated. In this study, 1519 perimenopausal women aged 40 to 65 years were selected from three urban communities in the Wuhan area, and two impoverished, mountainous communities in Hubei province, and followed from April to October 2014. Detailed information about demographic characteristics, menstruation, pregnancy, sexual life and chronic diseases was collected. A cross-sectional survey was carried out following information collection by Chi-square test and multiple logistic regression analysis. Univariate and multivariate logistic regression analysis demonstrated that the potential factors associated with developing SUI were old age (OR=3.4, 95% CI: 1.92-6.04), vaginal delivery (OR=0.623, 95% CI: 0.45-0.87), low income (OR=0.063, 95% CI: 0.40-0.92), atrophic vaginitis (OR=1.4, 95% CI: 1.03-1.80), pelvic organ prolapse (OR=2.81, 95% CI: 1.36-5.80), chronic pelvic pain (OR=2.17, 95% CI: 1.90-4.03), constipation (OR=1.44, 95% CI: 1.07-1.93) and incontinence of feces (OR=3.32, 95% CI: 2.03-5.43). Moreover, the ratio of SUI (33.2%) was higher than the ratio of urgency urinary incontinence (24.1%) or the ratio of mixed urinary incontinence (17.4%), and SUI had a greater impact on daily life among women with decreased sexual desire. In conclusion, SUI is a common disorder affecting over one third of the women surveyed, and has a severe impact on the daily life of perimenopausal women with declined sexual desire. Age, mode of delivery, and monthly income are major risk factors involved in the development of SUI.